Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 959 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3908. Min Range: -7.3908
Max Act: 7.3908. Min Act: -0.1700
Data Index: 8828679 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3908. Min Range: -7.3908
Max Act: 7.0783. Min Act: -0.1700
Data Index: 3579588 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3908. Min Range: -7.3908
Max Act: 6.9845. Min Act: -0.1700
Data Index: 1067758 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3908. Min Range: -7.3908
Max Act: 6.8283. Min Act: -0.1700
Data Index: 3054938 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3908. Min Range: -7.3908
Max Act: 6.7970. Min Act: -0.1700
Data Index: 6117270 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3908. Min Range: -7.3908
Max Act: 6.7345. Min Act: -0.1700
Data Index: 4819977 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3908. Min Range: -7.3908
Max Act: 6.7345. Min Act: -0.1700
Data Index: 919552 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3908. Min Range: -7.3908
Max Act: 6.7345. Min Act: -0.1700
Data Index: 5989275 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3908. Min Range: -7.3908
Max Act: 6.7033. Min Act: -0.1700
Data Index: 7660324 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3908. Min Range: -7.3908
Max Act: 6.7033. Min Act: -0.1700
Data Index: 3950153 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3908. Min Range: -7.3908
Max Act: 6.6720. Min Act: -0.1700
Data Index: 6711224 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3908. Min Range: -7.3908
Max Act: 6.6720. Min Act: -0.1700
Data Index: 4960519 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3908. Min Range: -7.3908
Max Act: 6.7033. Min Act: -0.1700
Data Index: 201074 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3908. Min Range: -7.3908
Max Act: 6.6408. Min Act: -0.1700
Data Index: 817943 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3908. Min Range: -7.3908
Max Act: 6.6408. Min Act: -0.1700
Data Index: 4247303 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3908. Min Range: -7.3908
Max Act: 6.6408. Min Act: -0.1700
Data Index: 390292 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3908. Min Range: -7.3908
Max Act: 6.6095. Min Act: -0.1700
Data Index: 4746175 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3908. Min Range: -7.3908
Max Act: 6.6095. Min Act: -0.1700
Data Index: 3970516 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3908. Min Range: -7.3908
Max Act: 6.5470. Min Act: -0.1700
Data Index: 6616127 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3908. Min Range: -7.3908
Max Act: 6.5783. Min Act: -0.1700
Data Index: 7511767 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #19